基于生成对抗网络的图像恢复与SLAM容错研究

为了提高即时定位与地图构建(SLAM)系统的容错能力,在经典图像生成网络Pix2Pix的基础上,逐步添加深度估计网络和深度信息的输入、基于STN网络的图像重建损失以及基于图像修复网络的图像补全损失3个方面的改进.结合双目图像的耦合关系,通过挖掘和融合多种信息,增大了信息的利用率,提高了模型的图像生成效果.提出将生成对抗网络(GAN)技术与SLAM容错场景相结合,直接实现了感知端的容错.在KITTI和Cityscapes数据集上进行实验,验证了改进模型的有效性.将模型生成的图像用于双目视觉系统的重建,验证了容错思想的可行性.

粗糙面SAR图像渐进式生成对抗网络

粗糙面合成孔径雷达(SAR)图像在遥感和目标识别等领域有着非常重要的意义。目前,粗糙面SAR图像的仿真方法主要有三种:数值法、统计法和解析法。数值法的计算复杂度会随着粗糙面尺寸的增大而升高,导致计算速度变慢,这限制了该方法的应用;统计法如空间相关模型是从统计角度生成SAR图像;解析法如基尔霍夫近似法(KA)等适用于计算粗糙面的散射矩阵。相干空变双向散射分布函数(CSVBSDF)物理模型可以生成多维度参数下的粗糙面的SAR图像,但其计算速度不能满足实时仿真需求。基于CSVBSDF,本文提出了一种粗糙面SAR图像渐进式生成对抗网络(RSPG),提高了SAR图像生成的速度。实验结果表明,生成的SAR图像与真实SAR图像在平均结构相似性指标上达到0.8,并且生成的速度与CSVBSDF相比得到了提高。

面向视频预测图像重建的感知损失函数

为了进一步提升视频预测网络重建场景图像的精确度,提出一种利用自编码器的多尺度判别器特征感知损失函数(MDF-AE):其核心是用一组面向不同尺度图像的判别器构成提取图像特征的损失网络;判别器网络通过单图像生成对抗网络(SinGAN)分阶段训练得到,训练中以图像自编码器作为生成器,在生成图像中引入图像重建误差,为视频预测网络进行未来图像帧的重建提供更准确的感知约束。实验结果表明,利用MDF-AE训练视频预测网络可有助于从结构、纹理和色彩上提升网络所重建场景图像的质量和可视化效果。

Low-dose CT image denoising method based on generative adversarial network

In order to solve the problems of artifacts and noise in low-dose computed tomography(CT)images in clinical medical diagnosis,an improved image denoising algorithm under the architecture of generative adversarial network(GAN)was proposed.First,a noise model based on style GAN2 was constructed to estimate the real noise distribution,and the noise information similar to the real noise distribution was generated as the experimental noise data set.Then,a network model with encoder-decoder architecture as the core based on GAN idea was constructed,and the network model was trained with the generated noise data set until it reached the optimal value.Finally,the noise and artifacts in low-dose CT images could be removed by inputting low-dose CT images into the denoising network.The experimental results showed that the constructed network model based on GAN architecture improved the utilization rate of noise feature information and the stability of network training,removed image noise and artifacts,and reconstructed image with rich texture and realistic visual effect.

Underwater Image Enhancement Based on Multi-scale Adversarial Network

In this study,an underwater image enhancement method based on multi-scale adversarial network was proposed to solve the problem of detail blur and color distortion in underwater images.Firstly,the local features of each layer were enhanced into the global features by the proposed residual dense block,which ensured that the generated images retain more details.Secondly,a multi-scale structure was adopted to extract multi-scale semantic features of the original images.Finally,the features obtained from the dual channels were fused by an adaptive fusion module to further optimize the features.The discriminant network adopted the structure of the Markov discriminator.In addition,by constructing mean square error,structural similarity,and perceived color loss function,the generated image is consistent with the reference image in structure,color,and content.The experimental results showed that the enhanced underwater image deblurring effect of the proposed algorithm was good and the problem of underwater image color bias was effectively improved.In both subjective and objective evaluation indexes,the experimental results of the proposed algorithm are better than those of the comparison algorithm.

A super-resolution reconstruction algorithm for mural images based on improved generative adversarial network

In order to solve the problem of the lack of ornamental value and research value of ancient mural paintings due to low resolution and fuzzy texture details,a super resolution(SR)method based on generative adduction network(GAN)was proposed.This method reconstructed the detail texture of mural image better.Firstly,in view of the insufficient utilization of shallow image features,information distillation blocks(IDB)were introduced to extract shallow image features and enhance the output results of the network behind.Secondly,residual dense blocks with residual scaling and feature fusion(RRDB-Fs)were used to extract deep image features,which removed the BN layer in the residual block that affected the quality of image generation,and improved the training speed of the network.Furthermore,local feature fusion and global feature fusion were applied in the generation network,and the features of different levels were merged together adaptively,so that the reconstructed image contained rich details.Finally,in calculating the perceptual loss,the brightness consistency between the reconstructed fresco and the original fresco was enhanced by using the features before activation,while avoiding artificial interference.The experimental results showed that the peak signal-to-noise ratio and structural similarity metrics were improved compared with other algorithms,with an improvement of 0.512 dB-3.016 dB in peak signal-to-noise ratio and 0.009-0.089 in structural similarity,and the proposed method had better visual effects.

改进的PF-AFN在虚拟试衣中的应用

针对PF-AFN中预测外观流精度欠缺和网络泛化能力较差的问题,提出改进的虚拟试衣网络.首先,增加目标人体预测模块,通过预测目标人体解析图像解耦形状与纹理;其次,依据仿射变换的共线特性,增加共线性损失项以约束形变过程,根据外观流的特性添加距离损失,弥补PF-AFN对局部区域约束不足的缺陷;最后,将生成的人体解析图像与原输入按通道拼接作为图像生成网络的输入,使用基于ResNet的类UNet++图像生成网络得到最终的试衣图像.基于VITON数据集,与其他4种最新方法进行对比实验,实验结果表明,该方法在图像相似度评价指标SSIM,FID和LPIPS上分别比其中最优方法提升了1.2%,11.1%和5.8%,图像清晰度和多样性评价(IS)与当前最优方法相当.从整体来看,所提方法改善了原网络中存在的问题,并取得了较好的视觉效果.

一种可隐藏敏感文档和发送者身份的区块链隐蔽通信模型

目前,区块链隐蔽通信的研究主要是通过发起多笔交易来传输一条短消息,这一方式不仅不适用于敏感数据量大的情况,还可能存在有些交易没有被打包而造成秘密信息的丢失,而且传输过程没有隐藏发送方身份.部分区块链隐蔽通信的研究中使用的图像隐写术虽然具有嵌入率高这一优点,但是越来越难以抵御基于统计特征的检测分析.针对以上问题,本文提出一种可隐藏敏感文档和发送者身份的区块链隐蔽通信模型.首先发送方使用密文策略的属性基加密(Ciphertext-Policy Attribute-Based Encryption,CP-ABE)对敏感文档进行加密,得到加密文档后将其上传至星际文件系统(Inter Planetary File System,IPFS);然后发送方利用基于生成式对抗网络(Generative Adversarial Networks,GAN)的图像隐写术将加密文档的哈希值嵌入载体图像中,得到载密图像后将其上传至IPFS;接着发送方创建一笔含有载密图像的哈希值的交易,交易经环签名之后广播到区块链网络中进行验证打包上链;之后,接收方从交易中读取载密图像的哈希值并通过上述步骤的逆过程得到加密文档;最后接收方根据CP-ABE设置的访问控制策略解密加密文档得到敏感文档.实验结果表明,该模型在传输秘密信息量上从KB提升至MB,而且具有较高的隐蔽性和安全性.

Gait recognition based on Wasserstein generating adversarial image inpainting network

Aiming at the problem of small area human occlusion in gait recognition,a method based on generating adversarial image inpainting network was proposed which can generate a context consistent image for gait occlusion area.In order to reduce the effect of noise on feature extraction,the stacked automatic encoder with robustness was used.In order to improve the ability of gait classification,the sparse coding was used to express and classify the gait features.Experiments results showed the effectiveness of the proposed method in comparison with other state-of-the-art methods on the public databases CASIA-B and TUM-GAID for gait recognition.